Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16785
    Prev
    Next
    INDEX
    Explanations

    phrases related to boasting or bragging

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boast" and its variations, indicating a focus on expressions of pride or claims of superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nton
    -0.70
    escal
    -0.65
    ondo
    -0.64
     poisoning
    -0.64
    ACTION
    -0.62
     outbreak
    -0.62
    avia
    -0.62
    Impl
    -0.60
     satur
    -0.60
     contam
    -0.60
    POSITIVE LOGITS
     boasted
    0.93
    ful
    0.91
     boasts
    0.89
    sonian
    0.83
     boasting
    0.83
     boast
    0.82
    fully
    0.78
    deck
    0.78
    indal
    0.78
    antly
    0.77
    Activations Density 0.018%

    No Known Activations